pjc
v1.220.0Korean-first harness for Claude Code: plan-feature, implement-task, pjc-systematic-debugging, DDD-friendly skills, 2-stage review subagents. Safety hooks run on pwsh 7 / Windows PowerShell, cross-platform (Windows verified, macOS/Linux experimental); skills are OS-agnostic.
By pjcLicense: MIT3 GitHub starsUpdated 38 minutes ago
Directory evidence
- Runtimes
- Claude Code
- Parsed components
- 8 skill or MCP entries
- Source updated
- Sep 2, 2026
- Manifest status
- Canonical path parsed
The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →
Install pjc for Claude Code
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install pjc@agent-plugin-marketplacePaste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.
The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.
Get the source manually
git clone https://github.com/jongcheol-pak/claude-harness-pjcClone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugins/pjc/.
Plugin files
├── .claude-plugin/plugin.json├── skills/add-domain-service/SKILL.md├── skills/add-viewmodel/SKILL.md├── skills/bootstrap-agents-md/SKILL.md├── skills/implement-task/SKILL.md├── skills/llm-wiki/SKILL.md├── skills/pjc-systematic-debugging/SKILL.md├── skills/plan-feature/SKILL.md└── skills/record-project-fact/SKILL.md
Included Skills8
This skill should be used when the user requests adding business logic, a domain service, an application service, or any logic that should live in the Domain or Application layer of a DDD project. Triggers on phrases like "서비스 추가", "도메인 로직", "비즈니스 로직", "use case 추가", "add service", "add use case". Generates Domain interface + implementation + DI registration + unit test scaffold. Do NOT trigger for logic that belongs inside a single Aggregate (add a method to the Aggregate instead), for pure UI/ViewModel work (use add-viewmodel), for infrastructure/config-only changes, or for projects without a Domain/Application layer split (single-project apps, scripts, or utilities with no DDD layering — forcing a nonexistent layer is wrong; implement directly per the project's structure).
This skill should be used when the user requests adding a new screen, dialog, page, window, or any UI component that needs a ViewModel in a WinUI 3 / WPF / MAUI project using CommunityToolkit.Mvvm. Triggers on phrases like "ViewModel 추가", "새 화면", "다이얼로그 추가", "페이지 만들기", "add screen/page/dialog/window". 화면이 앱 전역 상태(테마·언어·환경설정)를 다루더라도 요청 단위가 화면 하나면 이 스킬이며, 그 이유로 plan-feature에 넘기지 않는다 — 전역 기능이 들어간다는 것은 화면의 내용이지 요청 규모가 아니다. Generates ViewModel + View skeleton with proper MVVM bindings and DI registration. Do NOT trigger for non-XAML stacks (React/web, ASP.NET WebAPI controllers), simple UI text/label/style tweaks on an existing view, or debugging an existing ViewModel (use pjc-systematic-debugging). Android Jetpack ViewModel is out of scope.
This skill should be used when starting work on a project that has no AGENTS.md file, to generate one. Triggered automatically by plan-feature when AGENTS.md is missing, manually with "/pjc:bootstrap-agents-md", or when the user asks to create a project agent guide - e.g. "AGENTS.md 만들어줘", "프로젝트 가이드 문서 자동으로 만들어줘", "Claude가 이 프로젝트 컨벤션을 알게 해줘". 파일 이름을 대지 않고 목적만 말하는 요청도 이 스킬이다 — 빌드·실행·테스트 방법이나 프로젝트 규약을 정리한 문서를 새로 만들어 달라는 요청이 여기 해당한다. 그 경우에도 산출물은 AGENTS.md이며 README·ONBOARDING 등 다른 이름의 문서를 새로 만들지 않는다. Detects project stack from marker files (.csproj, package.json, pyproject.toml, go.mod, Cargo.toml, etc.) and generates a minimal AGENTS.md from one of 9 stack templates (plus generic/multi-stack). If stack is unknown, asks the user. Do NOT trigger when an AGENTS.md already exists, when only editing/adding a line to an existing AGENTS.md, or for writing a README. An existing CLAUDE.md does NOT block it — that file is Claude-only and usually gitignored, while AGENTS.md is committed and read by other agents.
This skill should be used when executing tasks from an approved plan.md. Triggers — ONLY when an approved plan.md already exists (or the user is approving a plan just presented) — on phrases like "구현", "implement", "이대로 진행", "진행해", "계속", "T<N> 진행", "go" (meaning "proceed with the plan"). If NO plan exists yet and the user asks to design or implement a non-trivial change, that is plan-feature first — it writes the plan, this skill runs it. Runs a FULLY AUTONOMOUS loop — processes ALL tasks (T1...Tn) without asking between tasks, stopping only when every task completes or a Halt Condition fires. Resuming mid-plan ("T6부터 계속") means T6 through the LAST task plus Phase F/G, not just T6. For trivial single-line edits without a plan, do NOT use this skill — Claude applies the change directly and lets hooks validate.
LLM WIKI(Obsidian vault) 운영·관리 스킬. 프로젝트를 위키에 추가/등록·정보 갱신(ingest)·삭제·상태 변경, 특정 기능/가이드/레시피를 위키에 추가, 위키 점검(lint)·질문(query)·복구(잘못 갱신된 페이지를 백업으로 되돌리기) 시 사용한다. "위키에 추가/등록", "{프로젝트} 위키에 등록", "위키 업데이트", "{프로젝트} 변경분 반영", "위키 점검/lint", "{기능} 위키에 추가", "위키 되돌려줘/복구", "큐 정리/pending 정리"(경량 큐 소비) 등의 요청에 발동. 코드 작업 세션의 read-only 참조(절차 K)는 이 스킬을 발동하지 않고 `references/lookup-rules.md`를 Read한다 — 자동으로 호출되는 것은 `pjc:implement-task` F-6.5가 구현 완료 후 대기 큐를 소비할 때(절차 M)뿐이다. 어느 디렉터리에서든(코드 프로젝트 폴더 포함) 호출 가능 — 위키 vault 밖에서도 동작한다. 단순 코드 수정·위키와 무관한 일반 지식 질문에는 발동하지 않는다(그건 plan-feature/implement-task 영역).
Use whenever the user reports a bug, test/build failure, runtime error, exception, crash, unexpected behavior, performance regression, memory leak, race condition, deadlock, or CI/CD issue. Triggers on Korean (버그/에러/오류/예외/크래시/안 됨/동작 안 함/이상해/왜 이래/왜 안 돼/이상한 현상/테스트 실패/빌드 실패/재현/디버깅) and English (bug/fix/debug/error/exception/crash/fails/broken/regression). Root cause investigation is mandatory before any patch. If the compiler/stack trace pinpoints the cause (file·line·reason) and the fix is a small single-file change, use the lightweight path, not a skip. Not for non-bug "fix" requests (reformatting/renaming — trivial edits, not debugging). Skip ONLY when the user explicitly asks to apply a fix they already diagnosed ("그냥 이 한 줄만 수정해줘, 원인 다 안다"). pjc/DDD-integrated variant (regression-test-first fix, spec-compliance review, cross-project llm-wiki lookup); prefer over generic systematic-debugging in pjc projects.
Plan a non-trivial code change into one plan.md — tasks, pre-resolved decisions, acceptance. 서술형 문제 제기(…해야 해/…안 된다)도 요청으로 본다. Triggers on Korean (계획/설계/기능 추가/리팩토링/구현/수정/변경/여러 곳/전체/만들어줘/앱·도구 만들어) and English (plan/design/implement/refactor/build an app/create a tool), a multi-task request, or a change spanning multiple files, altering logic/signatures, adding a function/class/method, or refactoring a resource layer (i18n/theming/DI). Routing — approved plan.md + execute-only (구현/이대로 진행/계속/T<N> 진행/go) → implement-task; bug/crash reports (버그/에러/크래시/안 됨/왜 안 돼) → pjc-systematic-debugging first; single-component work (Domain/Application service, ViewModel, wiki page) → add-domain-service/add-viewmodel/llm-wiki. Do NOT trigger for trivial edits (single-line text/label/color/size, typo, comment, config, ≤3-line code adding no new symbol/signature, or multi-element pure value substitution of any count — Claude edits directly). Ambiguous scope — ask "A) edit directly / B) make a plan".
Records a CONFIRMED project fact (build/run/test command, DB access, artifact location, untested layers) into an EXISTING AGENTS.md — on the suggest-agents-record hook's acceptance, or on request. Add, update, or remove. Triggers on "AGENTS.md에 기록", "빌드 명령 기록해줘", "DB 접근법 적어둬", "AGENTS.md에서 이 항목 빼줘". Also on injection-limit signals ("AGENTS.md가 너무 커졌어", "주입 상한 넘었어", the hook's "주입 상한 임박") — Step 5 relocates oversized sections and leaves a pointer. Also for RETROFIT ("AGENTS.md 정리해줘", "새 경계로 맞춰줘", "소급 정리") — measures, judges each section's destination, and hands off to plan-feature instead of editing. Do NOT trigger for creating a new AGENTS.md (use bootstrap-agents-md) or code work (plan-feature/implement-task). Writes to AGENTS.md ONLY, never CLAUDE.md, and only after showing the change and getting approval; the sole exception is Step 5's verbatim relocation, which reports afterward. Retrofit is not exempt — it deletes, so the plan is approved first. Real secrets are forbidden — env var names only.
Plugin manifests1
{
"name": "pjc",
"version": "1.220.0",
"description": "Korean-first harness for Claude Code: plan-feature, implement-task, pjc-systematic-debugging, DDD-friendly skills, 2-stage review subagents. Safety hooks run on pwsh 7 / Windows PowerShell, cross-platform (Windows verified, macOS/Linux experimental); skills are OS-agnostic.",
"author": {
"name": "pjc"
},
"homepage": "https://github.com/jongcheol-pak/claude-harness-pjc",
"repository": "https://github.com/jongcheol-pak/claude-harness-pjc",
"license": "MIT",
"displayName": "pjc Harness",
"keywords": [
"harness",
"korean",
"ddd",
"winui",
"dotnet",
"android",
"powershell",
"windows",
"plan-feature",
"pjc-systematic-debugging"
]
}For maintainers
If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.
[pjc on Agent Plugins Marketplace](https://pluginsmp.com/plugins/pjc)